© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30241
    Prev
    Next
    INDEX
    Explanations

    numbers relating to four

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    6
    -0.84
    ⑯
    -0.81
    ⑥
    -0.80
     lest
    -0.78
    TEMPO
    -0.77
    ▇
    -0.77
    ('../../
    -0.76
     rather
    -0.73
    ❻
    -0.73
    甚
    -0.73
    POSITIVE LOGITS
     fourth
    2.09
    4
    1.95
     quatrième
    1.80
    fourth
    1.73
    ４
    1.72
     four
    1.68
     ۴
    1.64
    cuatro
    1.63
     keempat
    1.63
     cuarta
    1.59
    Activations Density 0.066%

    No Known Activations